Offline Sentence Processing Measures for testing Readability with Users
نویسندگان
چکیده
While there has been much work on computational models to predict readability based on the lexical, syntactic and discourse properties of a text, there are also interesting open questions about how computer generated text should be evaluated with target populations. In this paper, we compare two offline methods for evaluating sentence quality, magnitude estimation of acceptability judgements and sentence recall. These methods differ in the extent to which they can differentiate between surface level fluency and deeper comprehension issues. We find, most importantly, that the two correlate. Magnitude estimation can be run on the web without supervision, and the results can be analysed automatically. The sentence recall methodology is more resource intensive, but allows us to tease apart the fluency and comprehension issues that arise.
منابع مشابه
Readability of French as a Foreign Language and its Uses
Reading is an important means of foreign language acquisition, particularly for vocabulary. Providing reading material that is of a suitable level of difficulty allows users to acquire vocabulary the most efficiently. Thus an on-line reading material recommender system for language learners requires a readability measure so that the difficulty of texts can be automatically assessed. However, mo...
متن کاملSentence Processing Among Native vs. Nonnative Speakers: Implications for Critical Period Hypothesis
The present study intended to investigate the processing behavior of 2 groups of L2 learners of English (high and mid in proficiency) and a group of English native speakers on English active and passive reduced relative clauses. Three sets of tasks, an offline task, and 2 online tasks were conducted. Results revealed that the high-proficiency group’s performance was the same as that of the nati...
متن کاملPsycholinguistic Models of Sentence Processing Improve Sentence Readability Ranking
While previous research on readability has typically focused on document-level measures, recent work in areas such as natural language generation has pointed out the need of sentence-level readability measures. Much of psycholinguistics has focused for many years on processing measures that provide difficulty estimates on a word-by-word basis. However, these psycholinguistic measures have not y...
متن کاملImproving Sentence-level Subjectivity Classification through Readability Measurement
We show that the quality of sentence-level subjectivity classification, i.e. the task of deciding whether a sentence is subjective or objective, can be improved by incorporating hitherto unused features: readability measures. Hence we investigate in 6 different readability formulae and propose an own. Their performance is evaluated in a 10-fold cross validation setting using machine learning. T...
متن کاملEvaluating Online Health Information: Beyond Readability Formulas
Although understanding health information is important, the texts provided are often difficult to understand. There are formulas to measure readability levels, but there is little understanding of how linguistic structures contribute to these difficulties. We are developing a toolkit of linguistic metrics that are validated with representative users and can be measured automatically. In this st...
متن کامل